Conditional GANs for Sonar Image Filtering with Applications to Underwater Occupancy Mapping

TL;DR

This paper introduces a novel cGAN-based method for filtering noisy sonar images, significantly improving underwater occupancy mapping accuracy for autonomous robots over traditional filtering techniques.

Contribution

The paper presents a new application of conditional GANs to produce noise-free sonar images, enhancing underwater perception and mapping capabilities.

Findings

cGAN outperforms conventional filtering methods in noise reduction

Improved accuracy in underwater occupancy mapping

Enhanced free and occupied space inference

Abstract

Underwater robots typically rely on acoustic sensors like sonar to perceive their surroundings. However, these sensors are often inundated with multiple sources and types of noise, which makes using raw data for any meaningful inference with features, objects, or boundary returns very difficult. While several conventional methods of dealing with noise exist, their success rates are unsatisfactory. This paper presents a novel application of conditional Generative Adversarial Networks (cGANs) to train a model to produce noise-free sonar images, outperforming several conventional filtering methods. Estimating free space is crucial for autonomous robots performing active exploration and mapping. Thus, we apply our approach to the task of underwater occupancy mapping and show superior free and occupied space inference when compared to conventional methods.